Research Reviewer I. VALIDITY AND RELIABILITY - In this section, the suggestions, corrections, and refinement of the draft may be explained fully thoroughly. The different persons involved in the correction and refinement of the research instrument may be mentioned. After the refinement of the instrument, testing the validity and reliability of the instrument may be done. 1. For validity - experts in line with the field of the study may be requested to go over the research instrument. Criteria for validation may be recommended and given to experts as their bases. It is the extent to which the scores from a measure represent the variable they are intended to Internal validity - refers to how well an experiment is done, especially whether it avoids confounding (more than one possible independent variable [cause] acting at the same time). The less chance for confounding in a study, the higher its internal validity is. Therefore, internal validity refers to how well a piece of research allows you to choose among alternate explanations of something. A research study with high internal validity lets you choose one explanation over another with a lot of confidence, because it avoids (many possible) confounds. External validity - refers to how well data and theories from one setting apply to another. This question is usually asked about laboratory research: Does it apply in the everyday "real" world outside the lab? 2. For reliability, the researcher may use any of the four methods. These are (1) test-retest, (2) splithalf, (3) parallel-form, and (4) internal consistency. If test-retest is used, the questionnaire is administered twice to the pilot sample with the same field of specialization in other institutions but not included as subjects of the study. Spearman rank difference correlation coefficient is used to determine the reliability of the responses. If the reliability value is high, it means that the research instrument is reliable, it is now ready to be administered to the subjects. Test-retest reliability - is the extent to which this is actually the case. For example, intelligence is generally thought to be consistent across time. A person who is highly intelligent today will be highly intelligent next week. This means that any good measure of intelligence should produce roughly the same scores for this individual next week as it does today. Clearly, a measure that produces highly inconsistent scores over time cannot be a very good measure of a construct that is supposed to be consistent. Split-half correlation This involves splitting the items into two sets, such as the first and second halves of the items or the even- and odd-numbered items. Then a score is computed for each set of items, and the relationship between the two sets of scores is examined. Internal consistency - is the consistency of people’s responses across the items on a multiple-item measure. Parallel-Forms Reliability One problem with questions or assessments is knowing what questions are the best ones to ask. A way of discovering this is do two tests in parallel, using different questions. Parallel-forms reliability evaluates different questions and question sets that seek to assess the same construct. Parallel-Forms evaluation may be done in combination with other methods, such as Split-half, which divides items that measure the same construct into two tests and applies them to the same group of people. The figure at the right summarize external and internal validity and the relation between the two. The green ellipse represents internal validity, and the blue rounded rectangle around it represents external validity, (focused in the present condition – what is); experimental design (future – what will be); and case study design (past, present and future). Four Parts of the Experimental Procedure 1. Selection of the appropriate materials for the tests; 2. Specification of the variable to be measured; 3. Selection of the procedure to be used in the measurement of the variable; and 4. Specification of the procedure to be used to determine whether the measurements support the hypothesis. Principles of a Research Design Replication Randomization Local control Control of extraneous variables Replication II. Research Design Research Design The success or failure of an investigation usually depends on the design of the experiment. It is a master plan specifying the methods and procedures for collecting and analyzing the needed information in a research study. Are of four kinds: historical design (focused in the past – what was); descriptive design A very essential element in the design of any research. Doing just the basic experiment is not enough. The experiment should be repeated several times to find an estimate of variations among observations on the group of subjects treated alike. Replication allows the researcher to assess the significance of the observed differences. Only through several repetitions of the experiment will make statistical test of significance possible. Randomization Refers to the assignment of the experimental subjects to the treatments by chance. It is done to create equivalent groups prior to the experiment. It tends to average out differences among groups. EXPERIMENTAL DESIGN Experimental Design: The Basic Building Blocks • • It reduces possible bias in comparative experiments. It also assures a valid or unbiased estimate of population parameters and the validity of the statistical test of significance. It is a problem-solving approach that the study is described in the future on what will be when certain variables are carefully controlled or manipulated. • This design is most useful in the natural sciences such as Botany, Zoology, Biology, Phycology, Ichthyology, Chemistry, Physics, Biochemistry, Molecular Biology, Microbiology, Biotechnology and many others. Experimental units are allocated to block in such a manner that the units within the block are relatively homogeneous. Experimental units may be blocked according to certain characteristics such as height, age, weight, gender, grade level, pH level, and so on. Control of Extraneous Variables Make sure that no outside or extraneous variables may affect the experimental subjects. Identical conditions must be provided for the control and experimental groups. These two groups should differ only in terms of the absence (control) or presence of the treatment (experimental) The principles of experimental design can be applied to SINGLE-FACTOR, TWOFACTOR and THREE-or more-FACTOR experiments. The general plan for selecting participants, assigning participants to experimental conditions, controlling extraneous variables, and gathering data. • Local Control Done when balancing, grouping and blocking of experimental units are employed in the adopted design. Experimental design …the researcher selects participants and divides them into two or more groups having similar characteristics and, then, applies the treatment(s) to the groups and measures the effects upon the groups. • An EXPERIMENTAL DESIGN is a description of what a researcher would like to find out and how to find it out. Types of Experimental Design 1. Single Group Design- The single group design is a design in which a group of subjects are administered a treatment and then measured (or observed). 2. Two-group design. Two comparable groups are employed as experimental and control groups. 3. Two-pair group design. This design is an elaboration of the two group design wherein there are two experimental groups and two control groups. 4. A pretest posttest design is an experiment where measurements are taken both before and after a treatment. The design means that you are able to see the effects of some type of treatment on a group. 5. 5. Randomized Complete Block Design (RCBD or RCB). This experimental design uses a group of test plants and animals as subjects of the study which are studied once but subsequent treatments applied are replicated to determine the cause of change. There is control in this design and the subjects will undergo randomization process. 6. 6. Complete Randomized Design. This is a design in which a group of test plants or animals is studied only once but subsequent (kasunod) or successive (sunod-sunod) treatment is applied to determine the cause of change. There is no control in this design but the subjects will undergo randomization process. 7. 7. Parallel-group design. This type of experimental design consists of three or more groups wherein one group is control group with two or more experimental groups. The control group or parallel group serves as control or basis for comparison of the experimental groups which is manipulated or changed, but the experimental groups vary. 8. 8. Three-group design. In this design, there are three groups of independent variables. 9. 9. Counter-balanced or Latin square design. This design is also called “rotation design”. It involves an exchange of two or more treatments taken by the subjects during the experiment. The arrangement employed in the design is Latin square in which each variable is a form of square occurring once in each row or column. This is called quasi-experimental design. 10. 10. Correlational design. This design is used to determine the relationship of two dependent variables (X and Y) on how they are manipulated by the independent variable. Single Group Design The single group design is a design in which a group of subjects are administered a treatment and then measured (or observed). Usually, with this design, an intact group of subjects is given the treatment and then measured or observed. No attempt is made to randomly assign subjects to the groups, nor does the design provide for any additional groups as comparisons. Single Group design does NOT have experimental group and control group The Two-Group Design Two-group design. Two comparable groups are employed as experimental and control groups. Experimental group – In a two-group design, the group of participants that receives the Independent Variable. Control group In a two-group design, the group of participants that does not receive the Independent Variable. Two-pair group design This design is an elaboration of the two group design wherein there are two experimental groups and two control groups. Parallel-group design This type of experimental design consists of three or more groups wherein one group is control group with two or more experimental groups. The control group or parallel group serves as control or basis for comparison of the experimental groups which is manipulated or changed, but the experimental groups vary. When will we use ANOVA? ANOVA is used when your research calls for comparison of the means of two or more groups. The F test is a global test and as such one test in an analysis is done. Therefore Parallel group design is a design in which two or more groups are used at the same time. This design has a control group, parallel group and experimental group. CONTROL GROUP- manipulated for change. EXPERIMENTAL GROUP- this is the group that varies. Parallel Group-Serves as control for comparative purposes. Pre-test and Post-test group design This design involves the experimental group and the control group which are carefully selected through randomization procedures. Both groups are given pretest at the beginning of the semester and posttest at the end of the semester. But the control group is isolated from all experimental influences. A pretest posttest design is an experiment where measurements are taken both before and after a treatment. The design means that you are able to see the effects of some type of treatment on a group. A pretest-posttest design is usually a quasiexperiment where participants are studied before and after the experimental manipulation. Remember, quasiexperimental simply means participants are not randomly assigned. It is possible to have a control group, or a group who doesn't receive the manipulation. In a pretestposttest design, there is only one group and all of them are in the experimental condition. The reason you run a pretest-posttest experiment is to see if your manipulation, the thing you're looking at, has caused a change in the participants. Since everyone is being manipulated in the same way, any changes you see across the group of participants is likely from the manipulation. This means you test them before doing the experiment, then you run your experimental manipulation, and then you test them again to see if there are any changes. Three-group design In this design, there are three groups of independent variables. Counter-balanced or Latin square design This design is also called “rotation design”. It involves an exchange of two or more treatments taken by the subjects during the experiment. The arrangement employed in the design is Latin square in which each variable is a form of square occurring once in each row or column. This is called quasi-experimental design. Complete Randomized Design This is a design in which a group of test plants or animals is studied only once but subsequent (kasunod) or successive (sunod-sunod) treatment is applied to determine the cause of change. There is no control in this design but the subjects will undergo randomization process. • Treatments are assigned randomly to the experimental subjects without restriction. • The experimental subjects in this case should be homogeneous with respect to all other factors which could affect the treatments being compared if they were not controlled. • It is flexible and is limited only by the number of experimental subjects. It is therefore possible that the number of replicates per treatment is not the same for the different groups. • Statistical analysis remains simple and easy even if some experimental subjects or an entire treatment group is missing. The loss of information due to missing observations is small compared to those with other design. It is appropriate to use CRD if the experimental subjects have the same characteristics and if several drop-outs are expected Using the CRD In single-factor experiments, only a single factor varies while all others are kept constant. The CRD can be used specially for experiments with homogeneous. Experimental units or in experiments where environmental effects are easily controlled like in laboratory experiments. This is rarely used in field experiments. Randomization can be accomplished by assigning treatments to experimental units entirely at random. This can be done by using a table of random numbers or by drawing lots. Randomized Complete Block Design (RCBD or RCB) The RCB is the standard design for agricultural experiments. This experimental design uses a group of test plants and animals as subjects of the study which are studied once but subsequent treatments applied are replicated to determine the cause of change. There is control in this design and the subjects will undergo randomization process. • Divides the experimental subjects into more or less homogenous groups called BLOCKS. • Blocking is done to make sure that the experimental subjects in a group have similar characteristics so that the observed differences among the groups will be largely due to the treatments. Disadvantages • Not easy to obtain experimental subjects with homogeneous characteristics. • The accuracy of the design is reduced when the subjects differ significantly. • Any variations between the experimental subjects enter into the experimental error. • Blocking also helps on giving more accurate results than the CRD. • The statistical test used may indicate significant differences among the treatments when actually there is none. • There are no restrictions as to the number of treatments or number of blocks in the experiments. Use of RCBD • The subjects can be categorized according to certain characteristics like gender, age, weight and height which can affect comparison of treatments. • A few drop-outs are expected. Using the RCBD • • • • • RCBD is used when randomization will tend to produce groups which are not nearly equivalent for comparison. This happen when the experimental subjects are not homogeneous but can be divided into more or less homogeneous groups or blocks in which each has subjects that have similar characteristics or properties. The experimental units in each block are randomly assigned to the different treatments so that the treatments are more or less alike in composition un terms of the subjects’ characteristics. RCBD is one of the most widely used experimental designs in field researchers. This is characterized by blocks of equal size, each of which contains a complete set of all treatments. RCBD reduces experimental error through proper blocking while retaining much of the flexibility and simplicity of the CRD. Blocking is done to reduce as much as possible heterogeneity among experimental units within each block. It increases the differences among blocks while leaving the subjects within a block more homogeneous. Except for different treatments, the assigned experimental units within each block should be managed as uniformly as possible. • The experimental area is divided into as many blocks as the number of replicates. Each block is then divided further into groups as many as the number of treatments. Randomization is then done separately for each block. It is specified that all treatments must appear once in each replication. Randomization may be done with the use of a table of random numbers. Correlational design This design is used to determine the relationship of two dependent variables (X and Y) on how they are manipulated by the independent variable. APA What is APA? American Psychological Association is the most commonly used format for manuscripts APA regulates Style In text Citations References A list of all sources used When is APA Style used? Term Papers Research Reports Empirical Studies Literature Reviews Theoretical Articles Methodological Articles Case Studies Where to place in-text citation In-text Citations: Paraphrase 1. Idea-focused- Placed the author(s) and date(s) in parentheses at a common appropriate place in or at the end of the sentence. A paraphrase is material from a source which has been summarized in your own words. Example: Researchers have pointed out that the lack of trained staff is a common barrier in providing adequate research education (Miranda, 2013). All paraphrases must be cited, using the author’s last name and year of publication. 2. Researcher-focused- Placed only the date in parentheses. Example: Miranda (2013) recommended that research education be required for college graduate in Philippines 3. Chronologically-focused- Integrate both the author and the date into the same sentence. Example- In 2001, Weist proposed using the Accounting and Teaching Scheme to analyze and develop accounting mental skill programs for college students. Text Citations Three types of text citations: 1. Paraphrase (summary) 2. Short Quote = less than 40 words 3. Long Quote= more than 40 words Three key points in APA citations 1. Use author, date format whenever possible. 2. If the source is quoted, you MUST include the page or paragraph number. 3. If author’s name is not available, use the title of the document in place of the author’s name No page number is required. Paraphrase : Example If the author’s name is a part of the sentence structure, the year follows the author’s names in parenthesis. Quotation marks are not included. Example: Author’s last name, year of publication Berk (2007) found that children begin to play organized games with rules, once they reach school-age. When the author’s name is not part of the sentence structure (parenthetical citation), the author’s name and year of publication are included at the end of the citation, in parenthesis. Quotation marks are not included. Example: Author’s last name, year of publication Studies conducted found that children begin to use organized play and games with rules at school-age (Berk, 2007 If the author’s name is part of the sentence, place only the year of publication in parentheses. Example: Berk (2007) found that children begin to play organized games with rules, once they reach school-age. When the author’s name is not part of the sentence, place both the name and the year, separated by a comma, in parentheses Berk (2007) found the following to be true: We have seen that middle childhood brings major advances in perspective taking, the capacity to imagine what other people may be thinking and feeling. These changes support self-esteem, understanding of others, and a wide variety of social skills. (p. 336) Example: Studies conducted found that children begin to use organized play and games with rules at school-age (Berk, 2007). Citations In-text Citations: Short Quote A direct quote is information included in a paper, which is taken directly from the source. Short quotes = less than 40 words Enclosed within quotation marks Cited using the author’s last name, year of publication, and page number (or paragraph number, if page number is not available.) Table 6.1 Basic Citation Styles Type of Citation First Citation in Text Subsequent Citations in Text One Author Two Authors Walker (2000) Walker (2000) Walker and Allen (2004) Walker and Allen (2004) (Walker & Allen, 2004) (Walker & Allen, 2004) Three Authors Bradley, Ramirez, and Soo (1999) Bradley, Ramirez, Soo, and Walsh (2006) Walker, Allen, Bradley, Ramiriz, and Soo (2008) Wasserstein et al. (2005) National Institute of Mental Health (NIMH, 2003) University of Pittsburgh (2005) Four Authors Five Authors Six + Authors Groups (abbrev.) Groups (no abbrev.) Short Quote (< 40 words) Examples “Reading makes use of many skills at once, taxing all aspects of our informationprocessing systems” (Berk, 2007, p. 306). Research has shown that “mathematics teaching in elementary school builds on and greatly enriches children’s informal knowledge of number concepts and counting” (Berk, 2007, p. 307). Long Quote (>40 words) Example Quotes over 40 words must be block formatted. Quotation marks are not used. The entire block quote is indented five spaces, and double-spaced. Example: Bradley et al. (1999) Bradley et al. (2006) Walker et al. (2008) Parenthetical Format, First Citations2007) (Walker, Parenthetical Format, Second Citations2007) (Walker, (Bradley, Ramirez, & (Bradley et al., 1999) Soo, 1999) (Bradley, Ramirez, Soo, (Bradley et al., 2006) & Walsh, 2006) (Walker, Allen, Bradley, (Walker et al., 2008) Ramirez, & Soo, 2008) Wasserstein et al. (2005) NIHM (2003) (Wasserstein et al., (Wasserstein et al., 2005) 2005) (National Institute of (NIMH, 2003) Mental Health [NIMH], 2003) University of Pittsburgh (University of Pittsburgh, (University of (2005) 2005) Pittsburgh, 2005) In-text Citations: Electronic sources When citing an electronic document, whenever possible, cite it in the authordate style. If electronic source lacks page numbers, locate and identify paragraph number or paragraph heading Example: Recent research has yielded similar results (Smith, 1997, para. 6). In-text Citations: Unknown author When the author’s name is designated as “Anonymous” cite in text the word Anonymous followed by a comma and the date. Example: (Anonymous, 1998) In the Reference list, an anonymous work is alphabetized by the word Anonymous as the author with the remaining publication data. EXAMPLES A. In-text citations help readers locate the cited source in the References section of the paper. Whenever you use a source, provide in parenthesis: When a work has no identified author, cite the title of the reference and the year. If it is a long title, use the first few words Use quotation marks around the title of an article, a chapter or a webpage • the author’s name and the date of publication • for quotations and close paraphrases, provide the author’s name, date of publication, and a page number Italicize the title of a journal, a book, a brochure or a report. Examples Recent research reveals (“Six Sites Meet,” 2006) significantly… Full publication title is “Six sites meet for comprehensive anti-gang initiative conference.” Notice the title was shortened for the in text citation because the title was long The book College Bound Seniors (2008) asserts that… Because there is no author listed for these sources, use the title in place of the author’s name in the citation and on the References page, in alphabetical order. Examples Recent research reveals (“Six Sites Meet,” 2006) significantly… The book College Bound Seniors (2008) asserts that… B. When quoting: • Introduce the quotation with a signal phrase • Include the author’s name, year of publication, and page number • Keep the citation brief—do not repeat the information Provide the author’s last name and the year of Introduce quotations with signal phrases, e.g.: publication in parenthesis after a summary or a paraphrase. According to Xavier (2008), “….” (p. 3). Xavier (2008) argued that “……” (p. 3). Use such signal verbs such as: acknowledged, contended, maintained, responded, reported, argued, concluded, etc. Use the past tense or the present perfect tense of verbs in signal phrases when they discuss past events. Include the author’s name in the signal phrase, followed by the year of publication in parenthesis. When the parenthetical citation includes two or more works, order them in the same way they appear in the reference list—the author’s name, the year of publication—separated by a semicolon. C. When including the quotation in a summary/paraphrase, also provide a page number in parenthesis after the quotation: When citing a work with two authors, use In the signal phrase, use “and” in between the authors’ names. (“Indiana,” 2008) Titles: Articles and Chapters = “ ” Books and Reports = italicize When citing an organization: In parenthesis, use “&” between names • mention the organization the first time you cite the source in the signal phrase or the parenthetical citation. • If the organization has a well-known abbreviation, include the abbreviation in brackets the first time the source is cited and then use only the abbreviation in later citations. When citing a work with three to five authors, identify all authors in the signal phrase or in parenthesis. Example: (Harklau, Siegal, & Losey, 1999) In subsequent citations, only use the first author's last name followed by "et al." in the signal phrase or in parentheses. Example: (Harklau et al., 1999) When citing a work with six and more authors, identify the first author’s name followed by “et al.” Example: Smith et al. (2006) maintained that…. (Smith et al., 2006) When citing authors with the same last names, use first initials with the last names. When citing a work of unknown author: • use the source’s full title in the signal phrase • cite the first word of the title followed by the year of publication in parenthesis. (B. Kachru, 2005; Y. Kachru, 2008) When citing two or more works by the same author and published in the same year, use lowercase letters (a, b, c) after the year of publication to order the references. Smith’s (1998a) study of adolescent According to “Indiana Joins Federal Accountability System” (2008) immigrants… OR When citing interviews, letters, e-mails, etc., include the communicator’s name, the fact that it was personal communication, and the date of the communication. Do not include personal communication in the reference list. When citing an electronic document, whenever possible, cite it in the author-date style. If electronic source lacks page numbers, locate and identify paragraph number/paragraph heading. EXAMPLES